Triple
T16657701
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Syl Johnson |
E404774
|
entity |
| Predicate | recordLabel |
P1500
|
FINISHED |
| Object | Hi Records |
E483444
|
NE FINISHED |
How this triple was built (2 steps)
Every LLM step that produced this triple, in pipeline order — named-entity classification, the disambiguation choices (the exact options shown, with the pick highlighted), and the generated description. The batch + timestamp of each is in the Provenance table below.
NER
Named-entity recognition
gpt-5-mini
Instruction
Given a phrase, classify it is english named entity (e.g., persons, organizations, works of art) in Latin script, or not (e.g., literals, dates, URLs, verbose phrases). For disambiguation, the statement where the phrase occurs as object is also given. Please return a JSON object with `phrase` (string, the phrase being analyzed) and `is_ne` (boolean, indicating whether the phrase is a Named Entity).
Input
Phrase: Hi Records | Statement: [Syl Johnson, recordLabel, Hi Records]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Hi Records Context triple: [Syl Johnson, recordLabel, Hi Records]
-
A.
Hi Records
chosen
Hi Records was a prominent Memphis-based soul and R&B label best known for releasing Al Green’s classic recordings in the 1960s and 1970s.
-
B.
Hub Records
Hub Records is an independent music label known for releasing the album "Stories Don’t End" by Dawes.
-
C.
Word Records
Word Records is a prominent American Christian music record label known for producing and distributing contemporary Christian and gospel artists.
-
D.
Enjoy Records
Enjoy Records is an independent music label known for releasing singer-songwriter and acoustic-driven albums such as Jack Johnson’s debut, "Brushfire Fairytales."
-
E.
Enjoy Records
Enjoy Records is an independent record label known for releasing music by artists such as Flake.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (3 batches)
The batch behind each pipeline step, in order, with when it ran. Timestamps are batch-level — stages were processed in waves, so the object chain (NER → NED1 → NEDg → NED2) reads in order, but predicate / elicitation batches can sit in a different wave.
| Step | Stage | Batch ID | Status | When |
|---|---|---|---|---|
| creating | Elicitation | batch_69d8838b5fbc81908c6575c132b82e80 |
completed | April 10, 2026, 4:58 a.m. |
| NER | Named-entity recognition | batch_69e37bfbfd7c819092c92f6c8da07dbd |
completed | April 18, 2026, 12:41 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a0084ccbc888190816cdf0ea67b0a90 |
completed | May 10, 2026, 1:14 p.m. |
Created at: April 10, 2026, 5:18 a.m.